Hugging Face's logo

chloeli
/
qwen-2.5-0.5B-instruct-sft-lora-countdown-optimal-1k-old

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
alignment-handbook
trl
sft
conversational
text-generation-inference
Model card Files Community
1
chloeli commited on
Commit
8bde0ae
·
verified ·
1 Parent(s): 678a6de

Training in progress, step 125

Browse files
Files changed (4) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. tokenizer.json +2 -2
  4. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -23,12 +23,12 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "up_proj",
27
  "gate_proj",
 
28
  "o_proj",
29
- "v_proj",
30
- "q_proj",
31
  "k_proj",
 
 
32
  "down_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
26
  "gate_proj",
27
+ "up_proj",
28
  "o_proj",
 
 
29
  "k_proj",
30
+ "q_proj",
31
+ "v_proj",
32
  "down_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4464ebe1df4b7869bc36574018e9b45b9c8f29fc56dc10a8a5dbea118fd91110
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b434cc27aff2367aa0bff36f200b98517a0c56180a82332e854dfd284b9ab8
3
  size 35237104
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0c439f7be467bf47d12a7e6f9adc6116201056fc60c67f431c679b7c16afc8
3
+ size 11422064
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9fdef951ae6b91fbc623cc85a81949317d857aba72039fd7914b758c5a5b341
3
  size 5944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b169b8f2514c28dd8cdc55757f1262ff107dac7487b40f373cb890dd9808579
3
  size 5944